Re: lowmem_reserve (replaces protection)

[Andrea Arcangeli]

On Wed, Oct 27, 2004 at 12:51:11AM -0400, Rik van Riel wrote:
> On Wed, 27 Oct 2004, Andrea Arcangeli wrote:
> 
> > what we'll happen is that we'll blindly free a few pages from each zone,
> > but then we'll be allowed to allocate the highmem pages, and not the
> > normal/dma pages. So after allocating the highmem pages we invoke kswapd
> > again and it frees again some highmem/normal/dma pages but we keep only
> > using the highmem ones.  So for a while we may be rolling over only the
> > highmem lru and ignoring all freed pages from the normal/dma zones.
> 
> This is not how the page allocator in 2.6 works.
> 
> It will not wake up kswapd until it is past the low
> watermark in all zones.

how else the page allocator should work if not waiting all zones to hit
the low+reserve watermarks? the page allocator works the same in 2.4
and 2.6, so I don't understand your point.

what changes is kswapd stop algorithm and the fact the lru is per-zone,
but I think I described correctly what happens in 2.6 kswapd-stop.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/